Abstract
Background: Pattern recognition technology allows for more intuitive control of myoelectric prostheses. However, the need to collect electromyographic data to initially train the pattern recognition system, and to re-train it during prosthesis use, adds complexity that can make using such a system difficult. Although experienced clinicians may be able to guide users to ensure successful data collection methods, they may not always be available when a user needs to (re)train their device. Methods: Here we present an engaging and interactive virtual reality environment for optimal training of a myoelectric controller. Using this tool, we evaluated the importance of training a classifier actively (i.e., moving the residual limb during data collection) compared to passively (i.e., maintaining the limb in a single, neutral orientation), and whether computational adaptation through serious gaming can improve performance. Results: We found that actively trained classifiers performed significantly better than passively trained classifiers for non-amputees (P < 0.05). Furthermore, collecting data passively with minimal instruction, paired with computational adaptation in a virtual environment, significantly improved real-time performance of myoelectric controllers. Conclusion: These results further support previous work which suggested active movements during data collection can improve pattern recognition systems. Furthermore, adaptation within a virtual guided serious game environment can improve real-time performance of myoelectric controllers.
| Original language | English (US) |
|---|---|
| Article number | 11 |
| Journal | Journal of neuroengineering and rehabilitation |
| Volume | 16 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 16 2019 |
Fingerprint
Keywords
- Amputee
- Electromyography
- Myoelectric control
- Pattern recognition
- Real-time adaptation
- Serious gaming
- Upper-limb prostheses
- Virtual guided training
- Virtual rehabilitation
ASJC Scopus subject areas
- Rehabilitation
- Health Informatics
Cite this
}
Adapting myoelectric control in real-time using a virtual environment. / Woodward, Richard B.; Hargrove, Levi J.
In: Journal of neuroengineering and rehabilitation, Vol. 16, No. 1, 11, 16.01.2019.Research output: Contribution to journal › Article
TY - JOUR
T1 - Adapting myoelectric control in real-time using a virtual environment
AU - Woodward, Richard B.
AU - Hargrove, Levi J
PY - 2019/1/16
Y1 - 2019/1/16
N2 - Background: Pattern recognition technology allows for more intuitive control of myoelectric prostheses. However, the need to collect electromyographic data to initially train the pattern recognition system, and to re-train it during prosthesis use, adds complexity that can make using such a system difficult. Although experienced clinicians may be able to guide users to ensure successful data collection methods, they may not always be available when a user needs to (re)train their device. Methods: Here we present an engaging and interactive virtual reality environment for optimal training of a myoelectric controller. Using this tool, we evaluated the importance of training a classifier actively (i.e., moving the residual limb during data collection) compared to passively (i.e., maintaining the limb in a single, neutral orientation), and whether computational adaptation through serious gaming can improve performance. Results: We found that actively trained classifiers performed significantly better than passively trained classifiers for non-amputees (P < 0.05). Furthermore, collecting data passively with minimal instruction, paired with computational adaptation in a virtual environment, significantly improved real-time performance of myoelectric controllers. Conclusion: These results further support previous work which suggested active movements during data collection can improve pattern recognition systems. Furthermore, adaptation within a virtual guided serious game environment can improve real-time performance of myoelectric controllers.
AB - Background: Pattern recognition technology allows for more intuitive control of myoelectric prostheses. However, the need to collect electromyographic data to initially train the pattern recognition system, and to re-train it during prosthesis use, adds complexity that can make using such a system difficult. Although experienced clinicians may be able to guide users to ensure successful data collection methods, they may not always be available when a user needs to (re)train their device. Methods: Here we present an engaging and interactive virtual reality environment for optimal training of a myoelectric controller. Using this tool, we evaluated the importance of training a classifier actively (i.e., moving the residual limb during data collection) compared to passively (i.e., maintaining the limb in a single, neutral orientation), and whether computational adaptation through serious gaming can improve performance. Results: We found that actively trained classifiers performed significantly better than passively trained classifiers for non-amputees (P < 0.05). Furthermore, collecting data passively with minimal instruction, paired with computational adaptation in a virtual environment, significantly improved real-time performance of myoelectric controllers. Conclusion: These results further support previous work which suggested active movements during data collection can improve pattern recognition systems. Furthermore, adaptation within a virtual guided serious game environment can improve real-time performance of myoelectric controllers.
KW - Amputee
KW - Electromyography
KW - Myoelectric control
KW - Pattern recognition
KW - Real-time adaptation
KW - Serious gaming
KW - Upper-limb prostheses
KW - Virtual guided training
KW - Virtual rehabilitation
UR - http://www.scopus.com/inward/record.url?scp=85060179177&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060179177&partnerID=8YFLogxK
U2 - 10.1186/s12984-019-0480-5
DO - 10.1186/s12984-019-0480-5
M3 - Article
VL - 16
JO - Journal of NeuroEngineering and Rehabilitation
JF - Journal of NeuroEngineering and Rehabilitation
SN - 1743-0003
IS - 1
M1 - 11
ER -